{"id":"https://openalex.org/W2117274752","doi":"https://doi.org/10.1109/icassp.2011.5947652","title":"Iterative feature normalization for emotional speech detection","display_name":"Iterative feature normalization for emotional speech detection","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2117274752","doi":"https://doi.org/10.1109/icassp.2011.5947652","mag":"2117274752"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947652","doi":"https://doi.org/10.1109/icassp.2011.5947652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947652","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072","observed_orcids":["https://orcid.org/0000-0002-4075-4072"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["Multimodal Signal Processing (MSP), Department of Electrical Engineering, University of Texas, Dallas, USA","Multimodal Signal Processing (MSP), Department of Electrical Engineering, The University of Texas at Dallas, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimodal Signal Processing (MSP), Department of Electrical Engineering, University of Texas, Dallas, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Multimodal Signal Processing (MSP), Department of Electrical Engineering, The University of Texas at Dallas, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064185910","display_name":"Angeliki Metallinou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Angeliki Metallinou","raw_affiliation_strings":["Speech Analysis and Interpretation Laboratory, Viterbi School of Engineering, University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Analysis and Interpretation Laboratory, Viterbi School of Engineering, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Shri Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204","observed_orcids":["https://orcid.org/0000-0002-1052-6204"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth S. Narayanan","raw_affiliation_strings":["Speech Analysis and Interpretation Laboratory, Viterbi School of Engineering, University of Southern California, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Analysis and Interpretation Laboratory, Viterbi School of Engineering, University of Southern California, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.1993,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.9870178,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5692","last_page":"5695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-normalization","display_name":"feature normalization","score":0.9070000052452087},{"id":"https://openalex.org/keywords/speaker-variability","display_name":"speaker variability","score":0.8230000138282776},{"id":"https://openalex.org/keywords/automatic-emotion-recognition","display_name":"automatic emotion recognition","score":0.7269999980926514},{"id":"https://openalex.org/keywords/acoustic-characteristics","display_name":"acoustic features","score":0.6349999904632568}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.9377106428146362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7174926996231079},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6070311069488525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.55935138463974},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.5441691279411316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.529429018497467},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4408620595932007},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947652","doi":"https://doi.org/10.1109/icassp.2011.5947652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947652","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.673.5128","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.673.5128","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sail.usc.edu/%7Emetallin/papers/Busso_icassp2011.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Reduced inequalities","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/10"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W99485238","https://openalex.org/W143173166","https://openalex.org/W175750906","https://openalex.org/W955355846","https://openalex.org/W1557133539","https://openalex.org/W2024490156","https://openalex.org/W2102298245","https://openalex.org/W2123864036","https://openalex.org/W2163026698","https://openalex.org/W2550557083","https://openalex.org/W6927634225","https://openalex.org/W6990412439"],"related_works":["https://openalex.org/W2010700035","https://openalex.org/W2526147887","https://openalex.org/W3010299549","https://openalex.org/W2091077707","https://openalex.org/W1976090878","https://openalex.org/W3013604122","https://openalex.org/W2062812718","https://openalex.org/W2126672039","https://openalex.org/W1997604360","https://openalex.org/W3195321095"],"abstract_inverted_index":{"Contending":[0],"with":[1,161],"signal":[2],"variability":[3],"due":[4],"to":[5,26,31,42,96],"source":[6],"and":[7,91,120,165],"channel":[8],"effects":[9,23],"is":[10,132,153],"a":[11,61,107],"critical":[12],"problem":[13,44],"in":[14,20,36],"automatic":[15],"emotion":[16,138],"recognition.":[17],"Any":[18],"approach":[19,41],"mitigating":[21],"these":[22,113],"however":[24],"has":[25,45],"be":[27,80],"done":[28],"so":[29],"as":[30],"not":[32],"compromise":[33],"emotion-relevant":[34],"information":[35],"the":[37,65,71,75,84,94,97,122,125,129,134,137,145,158,169],"signal.":[38],"A":[39],"promising":[40],"this":[43,104],"been":[46],"through":[47],"feature":[48,108],"normalization":[49,85,109,130,163,174],"using":[50,87],"features":[51],"drawn":[52],"from":[53],"non-emotional":[54],"(\"neutral\")":[55],"speech":[56,119],"samples.":[57],"This":[58,78],"paper":[59,105],"considers":[60],"scheme":[62,110],"for":[63],"minimizing":[64],"inter-speaker":[66],"differences":[67],"while":[68],"still":[69],"preserving":[70],"emotional":[72,101],"discrimination":[73],"of":[74,128,136,144],"acoustic":[76],"features.":[77,123],"can":[79],"achieved":[81],"by":[82,115],"estimating":[83],"parameters":[86,131],"only":[88,154],"neutral":[89,118],"speech,":[90],"then":[92],"applying":[93],"coefficients":[95],"entire":[98],"corpus":[99],"(including":[100],"set).":[102],"Specifically,":[103],"introduces":[106],"that":[111],"implements":[112],"ideas":[114],"iteratively":[116],"detecting":[117],"normalizing":[121],"As":[124],"approximation":[126],"error":[127],"reduced,":[133],"accuracy":[135,143],"detection":[139],"system":[140],"increases.":[141],"The":[142],"proposed":[146],"iterative":[147],"approach,":[148],"evaluated":[149],"across":[150],"three":[151],"databases,":[152],"2.5%":[155],"lower":[156],"than":[157,168],"one":[159,170],"trained":[160,171],"optimal":[162],"parameters,":[164],"9.7%":[166],"higher":[167],"without":[172],"any":[173],"scheme.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":4}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}